Skip to main content
The Krea 2 Image Node allows you to generate high-quality images from text prompts using Krea AI’s next-generation model. It supports two model variants, Krea 2 Medium for expressive illustrations and Krea 2 Large for expressive photorealism, with optional moodboard and style reference inputs.

​
What Krea 2 Text to Image is good at

  • Two model variants: Krea 2 Medium for expressive illustrations, Krea 2 Large for expressive photorealism
  • Style references: Apply the aesthetic style, mood, and visual direction of up to 10 reference images to your generation
  • Moodboard support: Use the moodboard_id parameter with a moodboard from Krea’s website
  • Adjustable generation settings: Control aspect ratio, resolution, creativity level, and seed
To use the Partner Nodes, you need to ensure that you are logged in properly and using a permitted network environment. Please refer to the Partner Nodes Overview section of the documentation to understand the specific requirements for using the Partner Nodes.
Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

​
Krea 2 Image Node Documentation

Check the following documentation for detailed node parameter settings:

​
Krea 2 Text to Image Workflow

Krea 2 Text to Image Workflow

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Krea2” in Template Library
  1. Enter your prompt: type a text description in the Krea2ImageNode
  2. Select a model variant: choose between Krea 2 Medium (illustrations) or Krea 2 Large (photorealism)
  3. Adjust parameters: set aspect ratio, resolution, creativity level, and seed
  4. Click Queue: press Ctrl+Enter or click the Queue button to generate
  5. View result: the generated image appears in the SaveImage node, saved to ComfyUI/output/

​
Krea 2 Style Reference Workflow

Krea 2 Style Reference Workflow The Style Reference workflow adds an extra step: upload one or more reference images that define the aesthetic style, mood, and visual direction. The generated image will match your prompt while applying the style from your reference images.

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Krea 2: Style Reference” in Template Library
  1. Upload reference images: use the LoadImage nodes to load style reference images (supports up to 10)
  2. Enter your prompt: describe the scene you want in the Krea2ImageNode
  3. Select a model variant: choose between Medium and Large
  4. Adjust style strength: modify the style reference strength in the Krea2StyleReferenceNode nodes
  5. Click Queue: press Ctrl+Enter to generate
  6. View result: the generated image appears in the SaveImage node

​
Additional Notes

  • The Krea 2 Image node supports up to 10 style reference images simultaneously
  • The moodboard_id parameter requires a valid UUID from a Krea moodboard on Krea’s website